Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Steven Eliuk"'
Autor:
Qinghan Xue, Panos Lampropoulos, Kenneth E. Barner, Yu Tian, Xiaolong Wang, Steven Eliuk, Xin Guo
Publikováno v:
EMNLP (Findings)
Catastrophic forgetting in neural networks indicates the performance decreasing of deep learning models on previous tasks while learning new tasks. To address this problem, we propose a novel Continual Learning Long Short Term Memory (CL-LSTM) cell i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9e576e48d3d54a436728b7ca8a4aa455
https://doi.org/10.18653/v1/2020.findings-emnlp.164
https://doi.org/10.18653/v1/2020.findings-emnlp.164
Publikováno v:
IEEE BigData
Fusion has been widely used in machine learning community, especially for problems dealing with multiple input sources and classifiers. The general strategy for information fusion in deep neural network is to directly concatenate the embedding featur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d489c488fe7622dca53ad4c70a1b183a
https://doi.org/10.1109/bigdata47090.2019.9006395
https://doi.org/10.1109/bigdata47090.2019.9006395
Publikováno v:
Intelligent Systems Reference Library ISBN: 9783319625294
Personal Assistants
Personal Assistants
During the last few years, deep learning has led to an astonishing advancement in visual recognition. Computers now reach near-human accuracy in visually recognizing characters, physical objects and human faces. This will certainly allow us to build
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::41b8116244e7d2bf3ecfdd3a58805b08
https://doi.org/10.1007/978-3-319-62530-0_6
https://doi.org/10.1007/978-3-319-62530-0_6
Publikováno v:
HPCC/SmartCity/DSS
A new scalable parallel math library, dMath, is presented that demonstrates leading scaling when using intranode, internode, and hybrid-parallelism for deep learning (DL). dMath provides easy-to-use distributed primitives and a variety of domain-spec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::637a32bf9b6fe97d561f8c6e84d31d1e
https://doi.org/10.1109/hpcc-smartcity-dss.2016.0096
https://doi.org/10.1109/hpcc-smartcity-dss.2016.0096
Publikováno v:
UbiComp Adjunct
We propose a novel wearable system that enables users to create their own object recognition system with minimal effort and utilize it to augment their memory. A client running on Google Glass collects images of objects a user is interested in, and s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a8154e5e3d20ca9f87d9f9f268f76c0
https://doi.org/10.1145/2968219.2968568
https://doi.org/10.1145/2968219.2968568
Publikováno v:
ELCVIA: electronic letters on computer vision and image analysis; Vol. 12, Núm. 1 (2013); p. 1-16
Recercat. Dipósit de la Recerca de Catalunya
instname
ELCVIA Electronic Letters on Computer Vision and Image Analysis, Vol 12, Iss 1 (2013)
Recercat: Dipósit de la Recerca de Catalunya
Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Scopus-Elsevier
Dipòsit Digital de Documents de la UAB
Universitat Autònoma de Barcelona
Recercat. Dipósit de la Recerca de Catalunya
instname
ELCVIA Electronic Letters on Computer Vision and Image Analysis, Vol 12, Iss 1 (2013)
Recercat: Dipósit de la Recerca de Catalunya
Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Scopus-Elsevier
Dipòsit Digital de Documents de la UAB
Universitat Autònoma de Barcelona
This paper provides an extensive analysis concerning runtime, accuracy and noise of High-Performance Computing (HPC) frameworks for Computed Tomography (CT) reconstruction tasks: "conventional" multi-core, multi threaded CPUs, the Compute Unified Dev
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d9749d8771bb13abc9551360e0127c73
http://www.raco.cat/index.php/ELCVIA/article/view/280899
http://www.raco.cat/index.php/ELCVIA/article/view/280899
Publikováno v:
VR
The recent advances in the fields such as modeling bio-mechanics of living tissues, haptic technologies, computational capacity, and graphics realism have created conditions necessary in order to develop effective surgical training using virtual envi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7185f850ec866647b92dfd35c6fcaf56
https://doi.org/10.1109/vr.2010.5444775
https://doi.org/10.1109/vr.2010.5444775